ASmiR: a machine learning framework for prediction of abiotic stress-specific miRNAs in plants

AdapTree: Data-Driven Approach to Assessing Plant Stress Through the AI-Sensor Synergy

This study investigates plant stress assessment by integrating advanced sensor technologies and Artificial Intelligence (AI). Multi-sensor data-including electrical impedance spectroscopy, temperature, and humidity-were used to capture plant physiological responses under environmental stress conditions. The key task addressed was the prediction of stress-related parameters using machine learning. A novel boosting-based ensemble method, AdapTree, combining AdaBoost and decision trees, was proposed to improve predictive accuracy and model interpretability. Experimental evaluation across multiple regression metrics demonstrated that AdapTree outperformed baseline models, achieving an R2 score of 0.993 for impedance magnitude prediction and 0.999 for both relative humidity (RH) and temperature, along with low root mean squared error (134.565 for impedance, 0.006966 for RH, and 0.0050099 for temperature) and mean absolute error values (22.789 for impedance; 1.51 × 10-5 for RH and 2.51 × 10-5 for temperature). These findings validate the reliability and effectiveness of the proposed AI-driven framework in accurately interpreting sensor data for plant stress detection. The approach offers a scalable, data-driven solution to enhance precision agriculture and agricultural sustainability. Furthermore, this method can be extended to monitor additional stress markers or applied across diverse plant species and field conditions, supporting future developments in intelligent crop monitoring systems.

Unveiling Salt Tolerance Mechanisms in Plants: Integrating the KANMB Machine Learning Model With Metabolomic and Transcriptomic Analysis

Salt stress presents a substantial threat to cereal crop productivity, especially in coastal agricultural regions where salinity levels are high. Addressing this challenge requires innovative approaches to uncover genetic resources that support molecular breeding of salt-tolerant crops. In this study, a novel machine learning model, KANMB is introduced, designed to analyze integrated multi-omics data from the natural halophyte Spartina alterniflora under various NaCl concentrations. Using KANMB, 226 metabolic biomarkers significantly linked to salt stress responses, grounded in metabolomic and transcriptomic profiles are identified. These biomarkers correlate with metabolic pathways associated with salt tolerance, providing insight into the underlying biochemical mechanisms. A co-expression analysis further highlights the MYB gene SaMYB35 as a pivotal regulator in the flavonoid biosynthesis pathway under salt stress. When overexpressed SaMYB35 in rice (ZH11) grown under high salinity, it triggers the upregulation of key flavonoid biosynthetic genes, elevates flavonoid content, and enhances salt tolerance compared to wild-type plants. The findings from this study offer a valuable genetic toolkit for breeding salt-tolerant cereal varieties and demonstrate the power of machine learning in accelerating biomarker discovery for stress resilience in non-model plant species.

Multi-Omic Advances in Olive Tree (Olea europaea subsp. europaea L.) Under Salinity: Stepping Towards 'Smart Oliviculture'

Soil salinisation is threatening crop sustainability worldwide, mainly due to anthropogenic climate change. Molecular mechanisms developed to counteract salinity have been intensely studied in model plants. Nevertheless, the economically relevant olive tree (Olea europaea subsp. europaea L.), being highly exposed to soil salinisation, deserves a specific review to extract the recent genomic advances that support the known morphological and biochemical mechanisms that make it a relative salt-tolerant crop. A comprehensive list of 98 olive cultivars classified by salt tolerance is provided, together with the list of available olive tree genomes and genes known to be involved in salt response. Na+ and Cl- exclusion in leaves and retention in roots seem to be the most prominent adaptations, but cell wall thickening and antioxidant changes are also required for a tolerant response. Several post-translational modifications of proteins are emerging as key factors, together with microbiota amendments, making treatments with biostimulants and chemical compounds a promising approach to enable cultivation in already salinised soils. Low and high-throughput transcriptomics and metagenomics results obtained from salt-sensitive and -tolerant cultivars, and the future advantages of engineering specific metacaspases involved in programmed cell death and autophagy pathways to rapidly raise salt-tolerant cultivars or rootstocks are also discussed. The overview of bioinformatic tools focused on olive tree, combined with machine learning approaches for studying plant stress from a multi-omics perspective, indicates that the development of salt-tolerant cultivars or rootstocks adapted to soil salinisation is progressing. This could pave the way for 'smart oliviculture', promoting more productive and sustainable practices under salt stress.

AScirRNA: A novel computational approach to discover abiotic stress-responsive circular RNAs in plant genome

In the realm of plant biology, understanding the intricate regulatory mechanisms governing stress responses stands as a pivotal pursuit. Circular RNAs (circRNAs), emerging as critical players in gene regulation, have garnered attention in recent days for their potential roles in abiotic stress adaptation. A comprehensive grasp of circRNAs' functions in stress response offers avenues for breeders to manipulating plants to develop abiotic stress resistant crop cultivars to thrive in challenging climates. This study pioneers a machine learning-based model for predicting abiotic stress-responsive circRNAs. The K-tuple nucleotide composition (KNC) and Pseudo KNC (PKNC) features were utilized to numerically represent circRNAs. Three different feature selection strategies were employed to select relevant and non-redundant features. Eight shallow and four deep learning algorithms were evaluated to build the final predictive model. Following five-fold cross-validation process, XGBoost learning algorithm demonstrated superior performance with LightGBM-chosen 260 KNC features (Accuracy: 74.55 %, auROC: 81.23 %, auPRC: 76.52 %) and 160 PKNC features (Accuracy: 74.32 %, auROC: 81.04 %, auPRC: 76.43 %), over other combinations of learning algorithms and feature selection techniques. Further, the robustness of the developed models were evaluated using an independent test dataset, where the overall accuracy, auROC and auPRC were found to be 73.13 %, 72.34 % and 72.68 % for KNC feature set and 73.52 %, 79.53 % and 73.09 % for PKNC feature set, respectively. This computational approach was also integrated into an online prediction tool, AScirRNA (https://iasri-sg.icar.gov.in/ascirna/) for easy prediction by the users. Both the proposed model and the developed tool are poised to augment ongoing efforts in identifying stress-responsive circRNAs in plants.

DBPMod: a supervised learning model for computational recognition of DNA-binding proteins in model organisms

DNA-binding proteins (DBPs) play critical roles in many biological processes, including gene expression, DNA replication, recombination and repair. Understanding the molecular mechanisms underlying these processes depends on the precise identification of DBPs. In recent times, several computational methods have been developed to identify DBPs. However, because of the generic nature of the models, these models are unable to identify species-specific DBPs with higher accuracy. Therefore, a species-specific computational model is needed to predict species-specific DBPs. In this paper, we introduce the computational DBPMod method, which makes use of a machine learning approach to identify species-specific DBPs. For prediction, both shallow learning algorithms and deep learning models were used, with shallow learning models achieving higher accuracy. Additionally, the evolutionary features outperformed sequence-derived features in terms of accuracy. Five model organisms, including Caenorhabditis elegans, Drosophila melanogaster, Escherichia coli, Homo sapiens and Mus musculus, were used to assess the performance of DBPMod. Five-fold cross-validation and independent test set analyses were used to evaluate the prediction accuracy in terms of area under receiver operating characteristic curve (auROC) and area under precision-recall curve (auPRC), which was found to be ~89-92% and ~89-95%, respectively. The comparative results demonstrate that the DBPMod outperforms 12 current state-of-the-art computational approaches in identifying the DBPs for all five model organisms. We further developed the web server of DBPMod to make it easier for researchers to detect DBPs and is publicly available at https://iasri-sg.icar.gov.in/dbpmod/. DBPMod is expected to be an invaluable tool for discovering DBPs, supplementing the current experimental and computational methods.

ASPTF: A computational tool to predict abiotic stress-responsive transcription factors in plants by employing machine learning algorithms

BACKGROUND

Abiotic stresses pose serious threat to the growth and yield of crop plants. Several studies suggest that in plants, transcription factors (TFs) are important regulators of gene expression, especially when it comes to coping with abiotic stresses. Therefore, it is crucial to identify TFs associated with abiotic stress response for breeding of abiotic stress tolerant crop cultivars.

METHODS

Based on a machine learning framework, a computational model was envisaged to predict TFs associated with abiotic stress response in plants. To numerically encode TF sequences, four distinct sequence derived features were generated. The prediction was performed using ten shallow learning and four deep learning algorithms. For prediction using more pertinent and informative features, feature selection techniques were also employed.

RESULTS

Using the features chosen by the light-gradient boosting machine-variable importance measure (LGBM-VIM), the LGBM achieved the highest cross-validation performance metrics (accuracy: 86.81%, auROC: 92.98%, and auPRC: 94.03%). Further evaluation of the proposed model (LGBM prediction method + LGBM-VIM selected features) was also done using an independent test dataset, where the accuracy, auROC and auPRC were observed 81.98%, 90.65% and 91.30%, respectively.

CONCLUSIONS

To facilitate the adoption of the proposed strategy by users, the approach was implemented as a prediction server called ASPTF, accessible at https://iasri-sg.icar.gov.in/asptf/. The developed approach and the corresponding web application are anticipated to supplement experimental methods in the identification of transcription factors (TFs) responsive to abiotic stress in plants.

CircRNA: An emerging star in plant research: A review

CircRNAs are a class of covalently closed non-coding RNA formed by linking the 5' terminus and the 3' terminus after reverse splicing. CircRNAs are widely found in eukaryotes, and they are highly conserved, with spatio-temporal expression specificity and stability. CircRNAs can act as miRNA sponges to regulate the expression of downstream target genes, regulating the transcription of parental genes and some can even be translated into peptides or proteins. Research on circRNAs in plants is still in its infancy compared to that in animals. With the deepening of research, the results of a variety of plant circRNAs suggest that they play an important role in growth and development, and tolerance towards abiotic stresses such as salt, drought, low temperature, high temperature and other adverse environments. In this review paper, we elaborated the molecular characteristics, mechanism of action, function and bioinformatics databases of plant circRNAs, combined with the progress of circRNA research in animals, discussed the potential mechanism of action of plant circRNAs, and proposed the unsolved problems and prospects for future application of plant circRNAs.

A review of artificial intelligence-assisted omics techniques in plant defense: current trends and future directions

Plants intricately deploy defense systems to counter diverse biotic and abiotic stresses. Omics technologies, spanning genomics, transcriptomics, proteomics, and metabolomics, have revolutionized the exploration of plant defense mechanisms, unraveling molecular intricacies in response to various stressors. However, the complexity and scale of omics data necessitate sophisticated analytical tools for meaningful insights. This review delves into the application of artificial intelligence algorithms, particularly machine learning and deep learning, as promising approaches for deciphering complex omics data in plant defense research. The overview encompasses key omics techniques and addresses the challenges and limitations inherent in current AI-assisted omics approaches. Moreover, it contemplates potential future directions in this dynamic field. In summary, AI-assisted omics techniques present a robust toolkit, enabling a profound understanding of the molecular foundations of plant defense and paving the way for more effective crop protection strategies amidst climate change and emerging diseases.

Machine learning provides specific detection of salt and drought stresses in cucumber based on miRNA characteristics

BACKGROUND

Specific detection of the type and severity of plant abiotic stresses helps prevent yield loss by considering timely actions. This study introduces a novel method to detect the type and severity of stress in cucumber plants under salinity and drought conditions. Various features, i.e., morphological (image textural features), physiological/biochemical (relative water content, chlorophyll, catalase activity, anthocyanins, phenol content, and proline), as well as miRNA characteristics (the concentration of miRNA-156a, miRNA-166i, miRNA-399g, and miRNA-477b) were extracted from plant leaves, and machine learning methods were used to predict the type and severity of stress by having these features. Support vector machine (SVM) with parameters optimized by genetic algorithm (GA) and particle swarm optimization (PSO) was used for machine learning.

RESULTS

The coefficient of determination of predicting the stress type and severity in plants under both stresses was 0.61, 0.82, and 0.99 using morphological, physiological/biochemical, and miRNA characteristics, respectively. This reveals machine learning methods optimized by metaheuristic optimization techniques can provide specific detection of salt and drought stresses in cucumber plants based on miRNA characteristics. Among the study miRNAs, miRNA-477b and miRNA-399g had the highest and lowest contribution to salt and drought stresses, respectively.

CONCLUSIONS

Comapred to conventional plant traits, miRNAs are more reliable features for providing us with valuable information about plant abiotic diseases at early stages. Using an electrochemical miRNA biosensor similar to one used in this work to measure the miRNA concentration in plant leaves and using a machine learning algorithm such as SVM enable farmers to detect the salt and drought stress at early stages in cucumber plants with very high accuracy.